Facial behavior analysis is a broad topic with various categories such as facial emotion recognition, age, and gender recognition. Many studies focus on individual tasks while the multi-task learning approach is still an open research issue and requires more research. In this paper, we present our solution and experiment result for the Multi-Task Learning challenge of the Affective Behavior Analysis in-the-wild competition. The challenge is a combination of three tasks: action unit detection, facial expression recognition, and valance-arousal estimation. To address this challenge, we introduce a cross-attentive module to improve multi-task learning performance. Additionally, a facial graph is applied to capture the association among action units. As a result, we achieve the evaluation measure of 128.8 on the validation data provided by the organizers, which outperforms the baseline result of 30.
This paper describes our submission to the fourth Affective Behavior Analysis (ABAW) competition. We proposed a hybrid CNN-Transformer model for the Multi-Task-Learning (MTL) and Learning from Synthetic Data (LSD) task. Experimental results on validation dataset shows that our method achieves better performance than baseline model, which verifies that the effectiveness of proposed network.
This paper proposes a novel Unified Feature Optimization (UFO) paradigm for training and deploying deep models under real-world and large-scale scenarios, which requires a collection of multiple AI functions. UFO aims to benefit each single task with a large-scale pretraining on all tasks. Compared with the well known foundation model, UFO has two different points of emphasis, i.e., relatively smaller model size and NO adaptation cost: 1) UFO squeezes a wide range of tasks into a moderate-sized unified model in a multi-task learning manner and further trims the model size when transferred to down-stream tasks. 2) UFO does not emphasize transfer to novel tasks. Instead, it aims to make the trimmed model dedicated for one or more already-seen task. With these two characteristics, UFO provides great convenience for flexible deployment, while maintaining the benefits of large-scale pretraining. A key merit of UFO is that the trimming process not only reduces the model size and inference consumption, but also even improves the accuracy on certain tasks. Specifically, UFO considers the multi-task training and brings two-fold impact on the unified model: some closely related tasks have mutual benefits, while some tasks have conflicts against each other. UFO manages to reduce the conflicts and to preserve the mutual benefits through a novel Network Architecture Search (NAS) method. Experiments on a wide range of deep representation learning tasks (i.e., face recognition, person re-identification, vehicle re-identification and product retrieval) show that the model trimmed from UFO achieves higher accuracy than its single-task-trained counterpart and yet has smaller model size, validating the concept of UFO. Besides, UFO also supported the release of 17 billion parameters computer vision (CV) foundation model which is the largest CV model in the industry.
Despite the remarkable progress in the development of predictive models for healthcare, applying these algorithms on a large scale has been challenging. Algorithms trained on a particular task, based on specific data formats available in a set of medical records, tend to not generalize well to other tasks or databases in which the data fields may differ. To address this challenge, we propose General Healthcare Predictive Framework (GenHPF), which is applicable to any EHR with minimal preprocessing for multiple prediction tasks. GenHPF resolves heterogeneity in medical codes and schemas by converting EHRs into a hierarchical textual representation while incorporating as many features as possible. To evaluate the efficacy of GenHPF, we conduct multi-task learning experiments with single-source and multi-source settings, on three publicly available EHR datasets with different schemas for 12 clinically meaningful prediction tasks. Our framework significantly outperforms baseline models that utilize domain knowledge in multi-source learning, improving average AUROC by 1.2%P in pooled learning and 2.6%P in transfer learning while also showing comparable results when trained on a single EHR dataset. Furthermore, we demonstrate that self-supervised pretraining using multi-source datasets is effective when combined with GenHPF, resulting in a 0.6%P AUROC improvement compared to models without pretraining. By eliminating the need for preprocessing and feature engineering, we believe that this work offers a solid framework for multi-task and multi-source learning that can be leveraged to speed up the scaling and usage of predictive algorithms in healthcare.
Facial affect analysis remains a challenging task with its setting transitioned from lab-controlled to in-the-wild situations. In this paper, we present novel frameworks to handle the two challenges in the 4th Affective Behavior Analysis In-The-Wild (ABAW) competition: i) Multi-Task-Learning (MTL) Challenge and ii) Learning from Synthetic Data (LSD) Challenge. For MTL challenge, we adopt the SMM-EmotionNet with a better ensemble strategy of feature vectors. For LSD challenge, we propose respective methods to combat the problems of single labels, imbalanced distribution, fine-tuning limitations, and choice of model architectures. Experimental results on the official validation sets from the competition demonstrated that our proposed approaches outperformed baselines by a large margin. The code is available at https://github.com/sylyoung/ABAW4-HUST-ANT.
Facial valence/arousal, expression and action unit are related tasks in facial affective analysis. However, the tasks only have limited performance in the wild due to the various collected conditions. The 4th competition on affective behavior analysis in the wild (ABAW) provided images with valence/arousal, expression and action unit labels. In this paper, we introduce multi-task learning framework to enhance the performance of three related tasks in the wild. Feature sharing and label fusion are used to utilize their relations. We conduct experiments on the provided training and validating data.
In this paper, we present the results of the HSE-NN team in the 4th competition on Affective Behavior Analysis in-the-wild (ABAW). The novel multi-task EfficientNet model is trained for simultaneous recognition of facial expressions and prediction of valence and arousal on static photos. The resulting MT-EmotiEffNet extracts visual features that are fed into simple feed-forward neural networks in the multi-task learning challenge. We obtain performance measure 1.3 on the validation set, which is significantly greater when compared to either performance of baseline (0.3) or existing models that are trained only on the s-Aff-Wild2 database. In the learning from synthetic data challenge, the quality of the original synthetic training set is increased by using the super-resolution techniques, such as Real-ESRGAN. Next, the MT-EmotiEffNet is fine-tuned on the new training set. The final prediction is a simple blending ensemble of pre-trained and fine-tuned MT-EmotiEffNets. Our average validation F1 score is 18% greater than the baseline convolutional neural network.
Facial expression in-the-wild is essential for various interactive computing domains. Especially, "Learning from Synthetic Data" (LSD) is an important topic in the facial expression recognition task. In this paper, we propose a multi-task learning-based facial expression recognition approach which consists of emotion and appearance learning branches that can share all face information, and present preliminary results for the LSD challenge introduced in the 4th affective behavior analysis in-the-wild (ABAW) competition. Our method achieved the mean F1 score of 0.71.
Causal Inference has wide applications in various areas such as E-commerce and precision medicine, and its performance heavily relies on the accurate estimation of the Individual Treatment Effect (ITE). Conventionally, ITE is predicted by modeling the treated and control response functions separately in their individual sample spaces. However, such an approach usually encounters two issues in practice, i.e. divergent distribution between treated and control groups due to treatment bias, and significant sample imbalance of their population sizes. This paper proposes Deep Entire Space Cross Networks (DESCN) to model treatment effects from an end-to-end perspective. DESCN captures the integrated information of the treatment propensity, the response, and the hidden treatment effect through a cross network in a multi-task learning manner. Our method jointly learns the treatment and response functions in the entire sample space to avoid treatment bias and employs an intermediate pseudo treatment effect prediction network to relieve sample imbalance. Extensive experiments are conducted on a synthetic dataset and a large-scaled production dataset from the E-commerce voucher distribution business. The results indicate that DESCN can successfully enhance the accuracy of ITE estimation and improve the uplift ranking performance. A sample of the production dataset and the source code are released to facilitate future research in the community, which is, to the best of our knowledge, the first large-scale public biased treatment dataset for causal inference.
This paper presents our system for the Multi-Task Learning (MTL) Challenge in the 4th Affective Behavior Analysis in-the-wild (ABAW) competition. We explore the research problems of this challenge from three aspects: 1) For obtaining efficient and robust visual feature representations, we propose MAE-based unsupervised representation learning and IResNet/DenseNet-based supervised representation learning methods; 2) Considering the importance of temporal information in videos, we explore three types of sequential encoders to capture the temporal information, including the encoder based on transformer, the encoder based on LSTM, and the encoder based on GRU; 3) For modeling the correlation between these different tasks (i.e., valence, arousal, expression, and AU) for multi-task affective analysis, we first explore the dependency between these different tasks and propose three multi-task learning frameworks to model the correlations effectively. Our system achieves the performance of $1.7607$ on the validation dataset and $1.4361$ on the test dataset, ranking first in the MTL Challenge. The code is available at https://github.com/AIM3-RUC/ABAW4.
Automatic affect recognition has applications in many areas such as education, gaming, software development, automotives, medical care, etc. but it is non trivial task to achieve appreciable performance on in-the-wild data sets. In-the-wild data sets though represent real-world scenarios better than synthetic data sets, the former ones suffer from the problem of incomplete labels. Inspired by semi-supervised learning, in this paper, we introduce our submission to the Multi-Task-Learning Challenge at the 4th Affective Behavior Analysis in-the-wild (ABAW) 2022 Competition. The three tasks that are considered in this challenge are valence-arousal(VA) estimation, classification of expressions into 6 basic (anger, disgust, fear, happiness, sadness, surprise), neutral, and the 'other' category and 12 action units(AU) numbered AU-{1,2,4,6,7,10,12,15,23,24,25,26}. Our method Semi-supervised Multi-task Facial Affect Recognition titled SS-MFAR uses a deep residual network with task specific classifiers for each of the tasks along with adaptive thresholds for each expression class and semi-supervised learning for the incomplete labels. Source code is available at https://github.com/1980x/ABAW2022DMACS.
Federated learning enables many applications benefiting distributed and private datasets of a large number of potential data-holding clients. However, different clients usually have their own particular objectives in terms of the tasks to be learned from the data. So, supporting federated learning with meta-learning tools such as multi-task learning and transfer learning will help enlarge the set of potential applications of federated learning by letting clients of different but related tasks share task-agnostic models that can be then further updated and tailored by each individual client for its particular task. In a federated multi-task learning problem, the trained deep neural network model should be fine-tuned for the respective objective of each client while sharing some parameters for more generalizability. We propose to train a deep neural network model with more generalized layers closer to the input and more personalized layers to the output. We achieve that by introducing layer types such as pre-trained, common, task-specific, and personal layers. We provide simulation results to highlight particular scenarios in which meta-learning-based federated learning proves to be useful.
A self-supervised multi-task learning (SSMTL) framework for video anomaly detection was recently introduced in literature. Due to its highly accurate results, the method attracted the attention of many researchers. In this work, we revisit the self-supervised multi-task learning framework, proposing several updates to the original method. First, we study various detection methods, e.g. based on detecting high-motion regions using optical flow or background subtraction, since we believe the currently used pre-trained YOLOv3 is suboptimal, e.g. objects in motion or objects from unknown classes are never detected. Second, we modernize the 3D convolutional backbone by introducing multi-head self-attention modules, inspired by the recent success of vision transformers. As such, we alternatively introduce both 2D and 3D convolutional vision transformer (CvT) blocks. Third, in our attempt to further improve the model, we study additional self-supervised learning tasks, such as predicting segmentation maps through knowledge distillation, solving jigsaw puzzles, estimating body pose through knowledge distillation, predicting masked regions (inpainting), and adversarial learning with pseudo-anomalies. We conduct experiments to assess the performance impact of the introduced changes. Upon finding more promising configurations of the framework, dubbed SSMTL++v1 and SSMTL++v2, we extend our preliminary experiments to more data sets, demonstrating that our performance gains are consistent across all data sets. In most cases, our results on Avenue, ShanghaiTech and UBnormal raise the state-of-the-art performance bar to a new level.
Depth estimation, visual odometry (VO), and bird's-eye-view (BEV) scene layout estimation present three critical tasks for driving scene perception, which is fundamental for motion planning and navigation in autonomous driving. Though they are complementary to each other, prior works usually focus on each individual task and rarely deal with all three tasks together. A naive way is to accomplish them independently in a sequential or parallel manner, but there are many drawbacks, i.e., 1) the depth and VO results suffer from the inherent scale ambiguity issue; 2) the BEV layout is directly predicted from the front-view image without using any depth-related information, although the depth map contains useful geometry clues for inferring scene layouts. In this paper, we address these issues by proposing a novel joint perception framework named JPerceiver, which can simultaneously estimate scale-aware depth and VO as well as BEV layout from a monocular video sequence. It exploits the cross-view geometric transformation (CGT) to propagate the absolute scale from the road layout to depth and VO based on a carefully-designed scale loss. Meanwhile, a cross-view and cross-modal transfer (CCT) module is devised to leverage the depth clues for reasoning road and vehicle layout through an attention mechanism. JPerceiver can be trained in an end-to-end multi-task learning way, where the CGT scale loss and CCT module promote inter-task knowledge transfer to benefit feature learning of each task. Experiments on Argoverse, Nuscenes and KITTI show the superiority of JPerceiver over existing methods on all the above three tasks in terms of accuracy, model size, and inference speed. The code and models are available at~\href{https://github.com/sunnyHelen/JPerceiver}{https://github.com/sunnyHelen/JPerceiver}.
Online presence on social media platforms such as Facebook and Twitter has become a daily habit for internet users. Despite the vast amount of services the platforms offer for their users, users suffer from cyber-bullying, which further leads to mental abuse and may escalate to cause physical harm to individuals or targeted groups. In this paper, we present our submission to the Arabic Hate Speech 2022 Shared Task Workshop (OSACT5 2022) using the associated Arabic Twitter dataset. The shared task consists of 3 sub-tasks, sub-task A focuses on detecting whether the tweet is offensive or not. Then, For offensive Tweets, sub-task B focuses on detecting whether the tweet is hate speech or not. Finally, For hate speech Tweets, sub-task C focuses on detecting the fine-grained type of hate speech among six different classes. Transformer models proved their efficiency in classification tasks, but with the problem of over-fitting when fine-tuned on a small or an imbalanced dataset. We overcome this limitation by investigating multiple training paradigms such as Contrastive learning and Multi-task learning along with Classification fine-tuning and an ensemble of our top 5 performers. Our proposed solution achieved 0.841, 0.817, and 0.476 macro F1-average in sub-tasks A, B, and C respectively.
Quantitative investment is a fundamental financial task that highly relies on accurate stock prediction and profitable investment decision making. Despite recent advances in deep learning (DL) have shown stellar performance on capturing trading opportunities in the stochastic stock market, we observe that the performance of existing DL methods is sensitive to random seeds and network initialization. To design more profitable DL methods, we analyze this phenomenon and find two major limitations of existing works. First, there is a noticeable gap between accurate financial predictions and profitable investment strategies. Second, investment decisions are made based on only one individual predictor without consideration of model uncertainty, which is inconsistent with the workflow in real-world trading firms. To tackle these two limitations, we first reformulate quantitative investment as a multi-task learning problem. Later on, we propose AlphaMix, a novel two-stage mixture-of-experts (MoE) framework for quantitative investment to mimic the efficient bottom-up trading strategy design workflow of successful trading firms. In Stage one, multiple independent trading experts are jointly optimized with an individual uncertainty-aware loss function. In Stage two, we train neural routers (corresponding to the role of a portfolio manager) to dynamically deploy these experts on an as-needed basis. AlphaMix is also a universal framework that is applicable to various backbone network architectures with consistent performance gains. Through extensive experiments on long-term real-world data spanning over five years on two of the most influential financial markets (US and China), we demonstrate that AlphaMix significantly outperforms many state-of-the-art baselines in terms of four financial criteria.
Handling various robot action-language translation tasks flexibly is an essential requirement for natural interaction between a robot and a human. Previous approaches require change in the configuration of the model architecture per task during inference, which undermines the premise of multi-task learning. In this work, we propose the paired gated autoencoders (PGAE) for flexible translation between robot actions and language descriptions in a tabletop object manipulation scenario. We train our model in an end-to-end fashion by pairing each action with appropriate descriptions that contain a signal informing about the translation direction. During inference, our model can flexibly translate from action to language and vice versa according to the given language signal. Moreover, with the option to use a pretrained language model as the language encoder, our model has the potential to recognise unseen natural language input. Another capability of our model is that it can recognise and imitate actions of another agent by utilising robot demonstrations. The experiment results highlight the flexible bidirectional translation capabilities of our approach alongside with the ability to generalise to the actions of the opposite-sitting agent.
Analyzing sports performance or preventing injuries requires capturing ground reaction forces (GRFs) exerted by the human body during certain movements. Standard practice uses physical markers paired with force plates in a controlled environment, but this is marred by high costs, lengthy implementation time, and variance in repeat experiments; hence, we propose GRF inference from video. While recent work has used LSTMs to estimate GRFs from 2D viewpoints, these can be limited in their modeling and representation capacity. First, we propose using a transformer architecture to tackle the GRF from video task, being the first to do so. Then we introduce a new loss to minimize high impact peaks in regressed curves. We also show that pre-training and multi-task learning on 2D-to-3D human pose estimation improves generalization to unseen motions. And pre-training on this different task provides good initial weights when finetuning on smaller (rarer) GRF datasets. We evaluate on LAAS Parkour and a newly collected ForcePose dataset; we show up to 19% decrease in error compared to prior approaches.
This paper addresses two major challenges in terahertz (THz) channel estimation: the beam-split phenomenon, i.e., beam misalignment because of frequency-independent analog beamformers, and computational complexity because of the usage of ultra-massive number of antennas to compensate propagation losses. Data-driven techniques are known to mitigate the complexity of this problem but usually require the transmission of the datasets from the users to a central server entailing huge communication overhead. In this work, we introduce a federated multi-task learning (FMTL), wherein the users transmit only the model parameters instead of the whole dataset, for THz channel and user direction-of-arrival (DoA) estimation to improve the communications-efficiency. We first propose a novel beamspace support alignment technique for channel estimation with beam-split correction. Then, the channel and DoA information are used as labels to train an FMTL model. By exploiting the sparsity of the THz channel, the proposed approach is implemented with fewer pilot signals than the traditional techniques. Compared to the previous works, our FMTL approach provides higher channel estimation accuracy as well as approximately 25 (32) times lower model (channel) training overhead, respectively.
Due to the short wavelength and large attenuation of millimeter-wave (mmWave), mmWave BSs are densely distributed and require beamforming with high directivity. When the user moves out of the coverage of the current BS or is severely blocked, the mmWave BS must be switched to ensure the communication quality. In this paper, we proposed a multi-camera view based proactive BS selection and beam switching that can predict the optimal BS of the user in the future frame and switch the corresponding beam pair. Specifically, we extract the features of multi-camera view images and a small part of channel state information (CSI) in historical frames, and dynamically adjust the weight of each modality feature. Then we design a multi-task learning module to guide the network to better understand the main task, thereby enhancing the accuracy and the robustness of BS selection and beam switching. Using the outputs of all tasks, a prior knowledge based fine tuning network is designed to further increase the BS switching accuracy. After the optimal BS is obtained, a beam pair switching network is proposed to directly predict the optimal beam pair of the corresponding BS. Simulation results in an outdoor intersection environment show the superior performance of our proposed solution under several metrics such as predicting accuracy, achievable rate, harmonic mean of precision and recall.